An extensive experimental study on segmenting online time series with error bound guarantee

An improved algorithm, i.e., HFSW, for segmenting online time series with error bound is proposed in our latest paper (IJMLC doi:10.1007/s13042-014-0310-9, 2014). Some researchers engaged in this filed read this paper and point out that there are two another existing strategies named FSW (IEEE TKDE doi:10.1109/TKDE.2008.29, 2008) and DisAlg (VLDBJ doi:10.1007/s00778-014-0355-0, 2014) which can also deal with the segmentation of online time series. And then, they want us to conduct some further experiments to demonstrate the effectiveness of our proposed method through comparing HFSW with FSW and DisAlg. Thus, we conduct such experimental comparison by testing 43 real datasets with the same fixed setting and further give the analysis to main difference among these algorithms.

The authors would like to thank the authors of [4] for their generous giving us their source code for the comparison tests in this paper. This work was supported by the Hebei Academy of Sciences Project (No. 15606 and No. 15605).

Authors and Affiliations

1. Faculty of Science, Agricultural University of Hebei, Baoding, 071001, China

   Ruiying Liu

2. Ocean College of Hebei Agricultural University, Qinhuangdao, 066003, China

   Lijun Wang

3. SJZ JKSS Technology Co. Ltd, Shijiazhuang, China

   Xueyan Guo & Huanyu Zhao

4. Institute of Applied Mathematics, Hebei Academy of Sciences, Shijiazhuang, China

   Xueyan Guo & Huanyu Zhao

Corresponding author

Correspondence to Huanyu Zhao.

Reprints and permissions